Unsupervised segmentation of brain tissue in multivariate MRI

In this paper, we present an unsupervised, automated technique for brain tissue segmentation based on multivariate magnetic resonance (MR) and spectroscopy images, for patients with gliomas. The algorithm uses spectroscopy data for coarse detection of the tumor region. Once the tumor area is identified, further processing is done on the FLAIR image in the neighborhood of the tumor to determine the hyper-intense abnormality in this region. Areas of contrast enhancement and necrosis are then identified by analyzing the FLAIR abnormality in gadolinium-enhanced T1-weighted images. The healthy brain tissue is then segmented into white matter, gray matter, and cerebrospinal fluid (CSF) using a hierarchical graphical model whose parameters are estimated using the EM algorithm.

[1]  Y. J. Zhang,et al.  A survey on evaluation methods for image segmentation , 1996, Pattern Recognit..

[2]  M. Berger,et al.  Histopathological validation of a three-dimensional magnetic resonance spectroscopy index as a predictor of tumor presence. , 2002, Journal of neurosurgery.

[3]  A Horsman,et al.  Tumour volume determination from MR images by morphological segmentation , 1996, Physics in medicine and biology.

[4]  R P Velthuizen,et al.  MRI: stability of three supervised segmentation techniques. , 1993, Magnetic resonance imaging.

[5]  Colin Studholme,et al.  An overlap invariant entropy measure of 3D medical image alignment , 1999, Pattern Recognit..

[6]  Christos Davatzikos,et al.  PROBABILISTIC SEGMENTATION OF BRAIN TUMORS BASED ON MULTI-MODALITY MAGNETIC RESONANCE IMAGES , 2007, 2007 4th IEEE International Symposium on Biomedical Imaging: From Nano to Macro.

[7]  Stephen M Smith,et al.  Fast robust automated brain extraction , 2002, Human brain mapping.

[8]  Mark Bernstein,et al.  Neuro-oncology, the Essentials , 2000, Journal of Neurology.

[9]  Stephen M. Smith,et al.  Segmentation of brain MR images through a hidden Markov random field model and the expectation-maximization algorithm , 2001, IEEE Transactions on Medical Imaging.

[10]  D. Vigneron,et al.  An automated technique for the quantitative assessment of 3D‐MRSI data from patients with glioma , 2001, Journal of magnetic resonance imaging : JMRI.

[11]  Richard M. Leahy,et al.  Surface-based labeling of cortical anatomy using a deformable atlas , 1997, IEEE Transactions on Medical Imaging.